1 / 20

EECS 442 – Computer vision

EECS 442 – Computer vision. Databases for object recognition and beyond. Segments of this lectures are courtesy of Prof F. Li, R. Fergus and A. Zisserman. Caltech 101. Pictures of objects belonging to 101 categories.

manny
Télécharger la présentation

EECS 442 – Computer vision

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. EECS 442 – Computer vision Databases for object recognition and beyond Segments of this lectures are courtesy of Prof F. Li, R. Fergus and A. Zisserman

  2. Caltech 101 • Pictures of objects belonging to 101 categories. • About 40 to 800 images per category. Most categories have about 50 images. • The size of each image is roughly 300 x 200 pixels.

  3. Caltech 101 images

  4. Caltech-101: Drawbacks • Smallest category size is 31 images: • Too easy? • left-right aligned • Rotation artifacts • Saturated performance

  5. Results up to 2007 -- recent methods obtain almost 100%

  6. Caltech-256 • Smallest category size now 80 images • About 30K images • Harder • Not left-right aligned • No artifacts • Performance is halved • More categories • New and larger clutter category

  7. Caltech 256 images baseball-bat dog basketball-hoop kayac traffic light

  8. The PASCAL Visual Object Classes (VOC) Dataset and Challenge Mark EveringhamLuc Van GoolChris WilliamsJohn WinnAndrew Zisserman

  9. Dataset Content • 20 classes: aeroplane, bicycle, boat, bottle, bus, car, cat, chair, cow, dining table, dog, horse, motorbike, person, potted plant, sheep, train, TV • Real images downloaded from flickr, not filtered for “quality” • Complex scenes, scale, pose, lighting, occlusion, ...

  10. OccludedObject is significantly occluded within BB Difficult Not scored in evaluation TruncatedObject extends beyond BB Pose Facing left Annotation • Complete annotation of all objects • Annotated in one session with written guidelines

  11. Examples Aeroplane Bicycle Bird Boat Bottle Bus Car Cat Chair Cow

  12. History • New dataset annotated annually • Annotation of test set is withheld until after challenge

  13. Other recent datasets ESP [Ahn et al, 2006] LabelMe [ Russell et al, 2005] TinyImage Torralba et al. 2007 Lotus Hill [ Yao et al, 2007] MSRC [Shotton et al. 2006]

  14. 3D object dataset [Savarese & Fei-Fei 07]

  15. Poses 72 • 8 azimuth angles • 3 zenith • 3 distances • ~ 7000 images! … … … … … … … … 1 1 2 … 10 Instances

  16. Largest dataset for object categories up to date J. Deng, H. Su. K. Li , L. Fei-Fei , • ~20K categories; • 14 million images; • ~700im/categ; • free to public at www.image-net.org

  17. http://www.image-net.org

  18. is a knowledge ontology • Taxonomy • Partonomy • The “social network” of visual concepts • Hidden knowledge and structure among visual concepts • Prior knowledge • Context

  19. More Datasets…. UIUC Cars (2004) S. Agarwal, A. Awan, D. Roth CMU/VASC Faces (1998) H. Rowley, S. Baluja, T. Kanade FERET Faces (1998) P. Phillips, H. Wechsler, J. Huang, P. Raus COIL Objects (1996) S. Nene, S. Nayar, H. Murase MNIST digits (1998-10) Y LeCun & C. Cortes KTH human action (2004) I. Leptev & B. Caputo Sign Language (2008) P. Buehler, M. Everingham, A. Zisserman Segmentation (2001) D. Martin, C. Fowlkes, D. Tal, J. Malik. 3D Textures (2005) S. Lazebnik, C. Schmid, J. Ponce CuRRET Textures (1999) K. Dana B. Van Ginneken S. Nayar J. Koenderink CAVIAR Tracking (2005) R. Fisher, J. Santos-Victor J. Crowley Middlebury Stereo (2002) D. Scharstein R. Szeliski

  20. Links to datasets The next tables summarize some of the available datasets for training and testing object detection and recognition algorithms. These lists are far from exhaustive. Databases for object localization Databases for object recognition On-line annotation tools Collections

More Related